pytrilogy 0.0.3.69__py3-none-any.whl → 0.0.3.70__py3-none-any.whl

{pytrilogy-0.0.3.69.dist-info → pytrilogy-0.0.3.70.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrilogy
-Version: 0.0.3.69
+Version: 0.0.3.70
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.3.69.dist-info → pytrilogy-0.0.3.70.dist-info}/RECORD

@@ -1,5 +1,5 @@
-pytrilogy-0.0.3.69.dist-info/licenses/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
-trilogy/__init__.py,sha256=cI0erWMqoxAN4RoZk4oMIaGKoFySaz8SJ8_yrbpiYwA,303
+pytrilogy-0.0.3.70.dist-info/licenses/LICENSE.md,sha256=5ZRvtTyCCFwz1THxDTjAu3Lidds9WjPvvzgVwPSYNDo,1042
+trilogy/__init__.py,sha256=jOvyFSWu8pnqklbm3VK_FmD5VSPj1cqSUoyMFyDKVC8,303
 trilogy/compiler.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/constants.py,sha256=lv_aJWP6dn6e2aF4BAE72jbnNtceFddfqtiDSsvzno0,1692
 trilogy/engine.py,sha256=OK2RuqCIUId6yZ5hfF8J1nxGP0AJqHRZiafcowmW0xc,1728
@@ -16,7 +16,7 @@ trilogy/core/env_processor.py,sha256=pFsxnluKIusGKx1z7tTnfsd_xZcPy9pZDungkjkyvI0
 trilogy/core/environment_helpers.py,sha256=VvPIiFemqaLLpIpLIqprfu63K7muZ1YzNg7UZIUph8w,8267
 trilogy/core/ergonomics.py,sha256=e-7gE29vPLFdg0_A1smQ7eOrUwKl5VYdxRSTddHweRA,1631
 trilogy/core/exceptions.py,sha256=jYEduuMehcMkmCpf-OC_taELPZm7qNfeSNzIWkDYScs,707
-trilogy/core/functions.py,sha256=poVfAwet1xdxTkC7WL38UmGRDpUVO9iSMNWSagl9_r4,29302
+trilogy/core/functions.py,sha256=R8_aOe2mNRgOLmsnI9pG_GOU3I7kFPTnXQzplN2d7Dw,29343
 trilogy/core/graph_models.py,sha256=wIT-oBchHWE46GLDkgN5K7EzhOBEo8LfaeWV5G5cYcE,3302
 trilogy/core/internal.py,sha256=iicDBlC6nM8d7e7jqzf_ZOmpUsW8yrr2AA8AqEiLx-s,1577
 trilogy/core/optimization.py,sha256=ojpn-p79lr03SSVQbbw74iPCyoYpDYBmj1dbZ3oXCjI,8860
@@ -81,7 +81,7 @@ trilogy/dialect/bigquery.py,sha256=e19dGcarapgA0x5_Xmq2StyHzuDWPOOPaR4elkWXwug,4
 trilogy/dialect/common.py,sha256=hhzuMTFW9QQIP7TKLT9BlJy6lw2R03a68jKQ-7t4-2c,6070
 trilogy/dialect/config.py,sha256=olnyeVU5W5T6b9-dMeNAnvxuPlyc2uefb7FRME094Ec,3834
 trilogy/dialect/dataframe.py,sha256=RUbNgReEa9g3pL6H7fP9lPTrAij5pkqedpZ99D8_5AE,1522
-trilogy/dialect/duckdb.py,sha256=C5TovwacDXo9YDpMTpPxkH7D0AxQERa7JL1RUkDGVng,3898
+trilogy/dialect/duckdb.py,sha256=gsXhPKX0D7ykJ9RFK9qx8uBTjLgtHu6PYv6GlBFtnJE,4448
 trilogy/dialect/enums.py,sha256=FRNYQ5-w-B6-X0yXKNU5g9GowsMlERFogTC5u2nxL_s,4740
 trilogy/dialect/postgres.py,sha256=VH4EB4myjIeZTHeFU6vK00GxY9c53rCBjg2mLbdaCEE,3254
 trilogy/dialect/presto.py,sha256=Wd0yHq3EOSfCOy7lWPfCr13JHO3olsm8qUXgml-oTm0,3529
@@ -97,9 +97,9 @@ trilogy/parsing/common.py,sha256=_5UEnLtu40VQ8gb6wg3GtSrxf6IONhEOntmdsm0X4lU,309
 trilogy/parsing/config.py,sha256=Z-DaefdKhPDmSXLgg5V4pebhSB0h590vI0_VtHnlukI,111
 trilogy/parsing/exceptions.py,sha256=Xwwsv2C9kSNv2q-HrrKC1f60JNHShXcCMzstTSEbiCw,154
 trilogy/parsing/helpers.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-trilogy/parsing/parse_engine.py,sha256=fKsV5eGe31oTVDEjeGSv_pb-222XaVRHtVgzFSnixZk,72439
+trilogy/parsing/parse_engine.py,sha256=vYhGmSJXi5TcLvt2mujISucQc35j4kHa78hj5ip9gGQ,72564
 trilogy/parsing/render.py,sha256=gGCFj2ue0UoaU2MR6qHGMAHXkYRMkTmHjnBowdcgFMY,19603
-trilogy/parsing/trilogy.lark,sha256=x9D1BXtE1E9Kxatx5Kt7xCaid8zgedabwca_B7j7L7o,14331
+trilogy/parsing/trilogy.lark,sha256=1RIqA7zrGuqDJYSv9yHGSw0vdIfGOLPOnc4hSBRSTVU,14346
 trilogy/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 trilogy/scripts/trilogy.py,sha256=1L0XrH4mVHRt1C9T1HnaDv2_kYEfbWTb5_-cBBke79w,3774
 trilogy/std/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -110,8 +110,8 @@ trilogy/std/money.preql,sha256=XWwvAV3WxBsHX9zfptoYRnBigcfYwrYtBHXTME0xJuQ,2082
 trilogy/std/net.preql,sha256=-bMV6dyofskl4Kvows-iQ4JCxjVUwsZOeWCy8JO5Ftw,135
 trilogy/std/ranking.preql,sha256=LDoZrYyz4g3xsII9XwXfmstZD-_92i1Eox1UqkBIfi8,83
 trilogy/std/report.preql,sha256=LbV-XlHdfw0jgnQ8pV7acG95xrd1-p65fVpiIc-S7W4,202
-pytrilogy-0.0.3.69.dist-info/METADATA,sha256=Je-V6aoBf1WujzpfMUFzAt1JduQTZ1ItagHgTRtubmU,9734
-pytrilogy-0.0.3.69.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pytrilogy-0.0.3.69.dist-info/entry_points.txt,sha256=ewBPU2vLnVexZVnB-NrVj-p3E-4vukg83Zk8A55Wp2w,56
-pytrilogy-0.0.3.69.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
-pytrilogy-0.0.3.69.dist-info/RECORD,,
+pytrilogy-0.0.3.70.dist-info/METADATA,sha256=dSEU2zgUrBXl88Yb-KV8y_hta24BeHt5VaPM19-YMFU,9734
+pytrilogy-0.0.3.70.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pytrilogy-0.0.3.70.dist-info/entry_points.txt,sha256=ewBPU2vLnVexZVnB-NrVj-p3E-4vukg83Zk8A55Wp2w,56
+pytrilogy-0.0.3.70.dist-info/top_level.txt,sha256=cAy__NW_eMAa_yT9UnUNlZLFfxcg6eimUAZ184cdNiE,8
+pytrilogy-0.0.3.70.dist-info/RECORD,,

trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.dialect.enums import Dialects
 from trilogy.executor import Executor
 from trilogy.parser import parse
 
-__version__ = "0.0.3.69"
+__version__ = "0.0.3.70"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

trilogy/core/functions.py

@@ -370,10 +370,10 @@ FUNCTION_REGISTRY: dict[FunctionType, FunctionConfig] = {
         arg_count=2,
     ),
     FunctionType.REGEXP_EXTRACT: FunctionConfig(
-        valid_inputs={DataType.STRING},
+        valid_inputs=[{DataType.STRING}, {DataType.STRING}, {DataType.INTEGER}],
         output_purpose=Purpose.PROPERTY,
         output_type=DataType.STRING,
-        arg_count=2,
+        arg_count=3,
     ),
     FunctionType.REGEXP_REPLACE: FunctionConfig(
         valid_inputs={DataType.STRING},

trilogy/dialect/duckdb.py

@@ -1,3 +1,4 @@
+import re
 from typing import Any, Callable, Mapping
 
 from jinja2 import Template
@@ -8,6 +9,19 @@ from trilogy.dialect.base import BaseDialect
 
 WINDOW_FUNCTION_MAP: Mapping[WindowType, Callable[[Any, Any, Any], str]] = {}
 
+SENTINAL_AUTO_CAPTURE_GROUP_VALUE = "-1"
+
+
+def generate_regex_extract(x: list[str]) -> str:
+    if str(x[2]) == SENTINAL_AUTO_CAPTURE_GROUP_VALUE:
+        regex = re.compile(x[1])
+        if regex.groups == 0:
+            search = 0
+        else:
+            search = 1
+        return f"REGEXP_EXTRACT({x[0]},{x[1]},{search})"
+    return f"REGEXP_EXTRACT({x[0]},{x[1]},{x[2]})"
+
 
 FUNCTION_MAP = {
     FunctionType.COUNT: lambda args: f"count({args[0]})",
@@ -37,6 +51,9 @@ FUNCTION_MAP = {
     FunctionType.DATETIME_LITERAL: lambda x: f"datetime '{x}'",
     # string
     FunctionType.CONTAINS: lambda x: f"CONTAINS(LOWER({x[0]}), LOWER({x[1]}))",
+    # regexp
+    FunctionType.REGEXP_CONTAINS: lambda x: f"REGEXP_MATCHES({x[0]},{x[1]})",
+    FunctionType.REGEXP_EXTRACT: lambda x: generate_regex_extract(x),
 }
 
 # if an aggregate function is called on a source that is at the same grain as the aggregate

trilogy/parsing/parse_engine.py

@@ -1802,6 +1802,9 @@ class ParseToObjects(Transformer):
 
     @v_args(meta=True)
     def fregexp_extract(self, meta, args):
+        if len(args) == 2:
+            # this is a magic value to represent the default behavior
+            args.append(-1)
         return self.function_factory.create_function(
             args, FunctionType.REGEXP_EXTRACT, meta
         )

trilogy/parsing/trilogy.lark

@@ -279,7 +279,7 @@
     _SUBSTRING.1: "substring("i
     fsubstring: _SUBSTRING expr "," expr "," expr ")"
     _REGEXP_EXTRACT.1: "regexp_extract("
-    fregexp_extract: _REGEXP_EXTRACT expr "," expr ")"
+    fregexp_extract: _REGEXP_EXTRACT expr "," expr ("," int_lit)? ")"
     _REGEXP_CONTAINS.1: "regexp_contains("
     fregexp_contains: _REGEXP_CONTAINS expr "," expr  ")"
     _REGEXP_REPLACE.1: "regexp_replace("